一款面向改进Yolov5的开源仓库,提供丰富的魔改方法
An Open Source Repository for Improving Yolov5, Providing Rich Magic Methods
改进方式教程
Tutorial on How to Improve
-
手把手带你YOLOv5/v7 (v5.0-v7.0)添加注意力机制(一)(并附上30多种顶会Attention原理图)🌟强烈推荐🍀新增8种
-
空间金字塔池化改进 SPP / SPPF / SimSPPF / ASPP / RFB / SPPCSPC / SPPFCSPC🚀
Performance
Model | size (pixels) |
mAPval 0.5:0.95 |
mAPval 0.5 |
Speed CPU b1 (ms) |
Speed V100 b1 (ms) |
Speed V100 b32 (ms) |
params (M) |
FLOPs @640 (B) |
Weights |
---|---|---|---|---|---|---|---|---|---|
YOLOv5n | 640 | 28.0 | 45.7 | 45 | 6.3 | 0.6 | 1.9 | 4.5 | YOLOv5n |
YOLOv5s | 640 | 37.4 | 56.8 | 98 | 6.4 | 0.9 | 7.2 | 16.5 | YOLOv5s |
YOLOv5m | 640 | 45.4 | 64.1 | 224 | 8.2 | 1.7 | 21.2 | 49.0 | YOLOv5m |
YOLOv5l | 640 | 49.0 | 67.3 | 430 | 10.1 | 2.7 | 46.5 | 109.1 | YOLOv5l |
YOLOv5x | 640 | 50.7 | 68.9 | 766 | 12.1 | 4.8 | 86.7 | 205.7 | YOLOv5x |
YOLOv5n6 | 1280 | 36.0 | 54.4 | 153 | 8.1 | 2.1 | 3.2 | 4.6 | YOLOv5n6 |
YOLOv5s6 | 1280 | 44.8 | 63.7 | 385 | 8.2 | 3.6 | 12.6 | 16.8 | YOLOv5s6 |
YOLOv5m6 | 1280 | 51.3 | 69.3 | 887 | 11.1 | 6.8 | 35.7 | 50.0 | YOLOv5m6 |
YOLOv5l6 | 1280 | 53.7 | 71.3 | 1784 | 15.8 | 10.5 | 76.8 | 111.4 | YOLOv5l6 |
YOLOv5x6 + TTA |
1280 1536 |
55.0 55.8 |
72.7 72.7 |
3136 - |
26.2 - |
19.4 - |
140.7 - |
209.8 - |
YOLOv5x6 |
SPP Structure Parameter and GFLOPs
Model | 参数量(parameters) | 计算量(GFLOPs) |
---|---|---|
SPP | 7225885 | 16.5 |
SPPF | 7235389 | 16.5 |
SimSPPF | 7235389 | 16.5 |
ASPP | 15485725 | 23.1 |
BasicRFB | 7895421 | 17.1 |
SPPCSPC | 13663549 | 21.7 |
SPPCSPC_group | 8355133 | 17.4 |
Others Structure Parameter and GFLOPs
Model | 参数量(parameters) | 计算量(GFLOPs) |
---|---|---|
TransposeConv upsampling | 7241917 | 16.6 |
InceptionConv | 7233597 | 16.2 |
BiFPN | 7384006 | 17.2 |
ShuffleNetv2 | 3844193 | 8.1 |
CARAFE | 7369445 | 17.0 |
Update log
2022.8.22 yolo.py Add Chinese annotations🍀2022.8.24 Add Demo of Pyqt page🍀